add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ح": 0, "ظ": 1, "ے": 2, "خ": 3, "ؤ": 4, "س": 5, "و": 6, "ر": 7, "چ": 8, "": 9, "ی": 10, "ڈ": 11, "م": 12, "ں": 13, "ذ": 14, "ھ": 15, "ٹ": 16, "ئ": 17, "آ": 18, "ت": 19, "ً": 20, "ص": 21, "د": 22, "ع": 23, "ا": 24, "غ": 25, "ِ": 26, "ہ": 27, "ن": 29, "ء": 30, "ط": 31, "ّ": 32, "گ": 33, "ض": 34, "ک": 35, "ج": 36, "ٔ": 37, "ڑ": 38, "ق": 39, "ب": 40, "ث": 41, "ز": 42, "ل": 43, "پ": 44, "ُ": 45, "ف": 46, "ژ": 47, "َ": 48, "ش": 49, "|": 28, "[UNK]": 50, "[PAD]": 51}
|